fix(statistic): Remove batch guessing and averaging in tp measuring #35
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Prep Steps
masterbranch (how?)step 6)Type of changes
Description
Purpose
To directly show the throughput for the given input, rather than trying to guess the batch dimension and report the value for a single sample, we drop the practice of using the first dimension as the batch for averaging.
Changes:
.github/workflows/minimal_test.yml: Specify bash shell for PR checkout commands to avoid using PowerShell in Windows.torchmeter/statistic.py: modify throughput measuring logic, directly use the reciprocal of the inference latency as the throughput of the model under a given input